AI agents invoke execute-command to trigger actions in iTerm MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool allows execution of arbitrary shell commands through iTerm2 terminals, which can have system-wide consequences (file manipulation, data exfiltration, privilege escalation, etc.). An AI agent with access could execute destructive commands, access sensitive data, modify system configuration, or compromise the host.
From the tool's definition Tool executes commands in a terminal via 'execute-command' with ability to run arbitrary shell commands. Description explicitly states 'command execution' and the sibling tools include 'read-output', confirming this is a code/command execution interface.
Documented attack patterns abuse exactly the kind of access execute-command gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and iTerm MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for execute-command:
{
"version": "1",
"default": "deny",
"tools": {
"execute-command": {
"limits": [
{
"counter": "execute-command_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}execute-command stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Execute a command in a specific terminal. It is categorised as a Execute tool in the iTerm MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the iTerm MCP Server MCP server in PolicyLayer and add a rule for execute-command: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches iTerm MCP Server. Nothing to install.
execute-command is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the execute-command rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for execute-command. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
execute-command is provided by the iTerm MCP Server MCP server (rishabkoul/iterm-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from iTerm MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
5 iTerm MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.